Model Context Protocol 40

Knowledge graph for precise AI coding-agent codebase context GitNexus is an open-source knowledge graph engine by Akon Labs that indexes codebases into a deterministic graph of dependencies, callers, imports, call chains, execution flows, clusters, and cross-repository relationships. It connects to coding agents through MCP, allowing them to query structured code context instead of relying only on file searches, embeddings, or similarity guesses. GitNexus supports impact analysis, blast-radius detection, git-diff analysis, architecture discovery, hybrid search, and multi-repository graph analysis. Its local version keeps code, indexing, and queries on the user's machine, while Enterprise provides managed SaaS or self-hosted deployments with features such as automated PR review, auto-reindexing, unified multi-repo graphs, SSO, and dedicated support.

Open-source autonomous observability tool that instruments code and automatically fixes bugs. Superlog is an open-source autonomous observability tool that automatically installs itself, instruments repositories with OpenTelemetry, and monitors codebases without manual setup or vendor lock-in. When anomalies or system failures occur, it fingerprints and groups noisy repeated logs into a single clear incident. It then performs a root-cause analysis, provides severity scores, assesses the impact, and creates automated resolution pull requests directly in Slack to help engineering teams fix bugs immediately.

Observability and monitoring platform for Model Context Protocol (MCP) servers. Spanly is a dedicated observability and monitoring platform built specifically for Model Context Protocol (MCP) servers. It provides SaaS engineering teams with full visibility into their MCP traffic, tracking error rates, session traces, latencies, client analytics, and deployment alerts at the protocol level. Unlike standard APM tools that capture basic HTTP requests, Spanly captures full JSON-RPC packets (arguments, results, errors, and timings) across any programming language without requiring complex code changes. It works alongside existing infrastructure monitoring tools like Datadog, Sentry, or New Relic to deliver complete protocol-aware telemetry for production AI agent environments.

VeilStrat tracks real-time AI adoption signals so you know which companies are buying, building, or evaluating AI - before your competitors do. VeilStrat is a B2B intelligence platform that surfaces AI adoption signals across the market, helping sales, marketing, and strategy teams identify which companies are actively investing in artificial intelligence. Instead of guessing who your next customer is, VeilStrat tells you who is hiring AI talent, deploying new AI tools, publishing AI initiatives, or showing buying intent, all from public data sources, refreshed continuously. Built for go-to-market teams, founders, and investors, Veilstrat turns scattered public signals into a clear picture of demand. Track AI adoption by company, industry, and region. Spot emerging buyers early. Prioritize outreach toward accounts already moving on AI rather than cold prospects who aren't ready. Beyond buyer intelligence, VeilStrat publishes Playbooks for developers and AI builders. The MCP server directory is a curated, searchable database of 12,000+ Model Context Protocol servers, letting you connect AI agents to APIs, databases, browsers, and external tools without wiring up each integration from scratch. Every server is verified, scored, and ready to install, with coverage for clients like Claude Code, Codex, Cursor, and any other MCP-compatible agent. Alongside it, the Skills and Bundles playbooks help developers extend agent capabilities and ship faster. Whether you're hunting for the right GitHub, Playwright, or AWS MCP server, or browsing official versus community options, Veilstrat's directory is built to be the fastest way to find and connect the tools your agents need. Key use cases include AI-focused lead generation, account-based marketing, competitive intelligence, market research, and AI agent tooling discovery. If your work depends on the AI wave - selling into it, building on it, or both, VeilStrat helps you find the companies and the tools that matter, faster and with sharper targeting than traditional methods.

Composio MCP connects apps to LLMs, IDEs, & Claude with 250+ MCP Servers. Composio-MCP offers 250+ managed MCP server implementations, enabling seamless app integration with hosts like Claude, Cursor, Windsurf, and your agents. Just one line of code connects apps to your preferred MCP hosts effortlessly. Composio MCP: Connect LLMs, IDEs, & Claude with 250+ MCP Server - Composio. Connect your Agents with 15k+ tools through Composio’s Model Context Protocol (MCP) servers

Injects undocumented team tribal knowledge and PR history into AI coding agents. KodHau MCP is a governance layer for AI agents designed to inject 'tribal knowledge' into development workflows. It acts as an MCP server that runs locally, scanning a team's PR history, architecture decisions, and undocumented review comments to provide context to AI tools like Cursor and Claude Code. By surfacing the 'why' behind existing code before an agent makes changes, it prevents AI from making naive or destructive suggestions that violate established institutional constraints.

Open-source integration infrastructure for AI agents and third-party applications Corsair is an open-source integration layer for AI agents and applications. It provides secure, multi-tenant OAuth authentication, permissions, MCP support, webhooks, credential management, caching, and provider-specific error handling for services such as Gmail, Slack, Notion, HubSpot, Airtable, Google Calendar, Stripe, Linear, GitHub, and Discord. Developers can self-host the SDK for free or use Corsair's managed cloud platform to connect third-party applications without maintaining authentication flows, token rotation, webhook verification, API changes, rate-limit handling, and tenant credential isolation.

MindsDB: AI data automation solution connecting enterprise data for real-time decision-making using SQL. MindsDB is an Enterprise Data Platform for AI that enables users to apply the power of OpenAI's GPT-3 and Hugging Face models to the text data in their database using simple SQL commands. It allows for automatic classification, labeling of text columns, message creation, summarization, translation, and more. MindsDB connects and unifies petabyte-scale enterprise data, enabling enterprise-wide informed decision-making in real-time. It operates as a cognitive engine that can operate anywhere, understands complex questions in the context of organizational data, retrieves knowledge across structured and unstructured data platforms, delivers actionable insights, provides transparency into its thinking process, and ensures data privacy.

An AI platform for rapid building, testing, and deploying ChatGPT and MCP applications. Fractal is an AI-powered development platform designed for the rapid creation, testing, and deployment of ChatGPT and Model Context Protocol (MCP) applications. It streamlines the app-building process by providing a Smart Architecture Planner, a specialized AI coding agent, and a native emulator to test apps directly within the development environment. Built by MIT alumni, the platform handles the technical complexities of infrastructure and deployment, allowing indie builders and enterprise teams to turn ideas into live products in minutes rather than weeks.

TypeScript framework for building, deploying, and observing AI agents Mastra is an open-source TypeScript framework for building, deploying, observing, and improving AI agents and AI-powered applications. It provides agent development tools, typed workflows, memory, workspaces, MCP support, human-in-the-loop functionality, model routing, and built-in observability. Developers can use Mastra with React, Next.js, Node.js, Hono, and other JavaScript or TypeScript environments to create internal automation agents, customer-facing assistants, developer platforms, and multi-step workflow applications. Mastra projects can be self-hosted under the Apache 2.0 license or deployed through Mastra Platform with managed infrastructure, monitoring, storage, and enterprise capabilities.

Global search engine for Model Context Protocol (MCP) tools and AI agents. MCPAgentSeek is a global search engine for Model Context Protocol (MCP) tools and AI agents. It is a comprehensive international search platform offering smart recommendations for databases, browser automation, AI assistants, and more. It helps users find the perfect MCP tools and AI agents for their projects, enabling AI to better connect with and operate data and applications.

Interactive platform for exploring, testing, and integrating MCP APIs. MCP Showcase is an interactive platform that provides a live, no-risk MCP playground for companies to explore, chat with, and integrate their Model Context Protocol (MCP) APIs in minutes. It aims to accelerate evaluation and drive higher integration rates for MCP servers by delighting developers and convincing decision-makers. The platform offers a sandbox environment for testing MCP functionality, interactive documentation, chat features, and real-time usage insights to refine product features and improve API design.

Self-driving company brain providing shared memory and context for AI tools. Hyper is a self-driving company brain that acts as a shared memory for AI. It securely and quietly synthesizes data from a team's tools—such as Docs, Slack, Email, and Calendar—and plugs that context directly into existing AI tools like Claude, Cursor, Codex, and ChatGPT. By transforming AI agents from forgetful interns into seasoned veterans, it enables them to draft emails in your voice, read contracts, triage tickets, and prepare for meetings without requiring manual prompts or complex setup.

A self-maintaining company knowledge layer for more accurate AI agents Pensieve is an AI context layer that connects to a company's tools and builds a continuously updated understanding of its business. It organizes information from sources such as Slack, Notion, Google Drive, GitHub, HubSpot, databases, billing systems, analytics, and internal APIs into a navigable company knowledge map. AI tools including Claude, Cursor, ChatGPT, Codex, and custom agents can access this context through MCP, helping them provide more accurate answers without repeatedly searching and relearning company information.

Ground AI research agents in trusted computer science papers and research tools. Lune Research is an MCP server that connects AI agents to trusted scientific research knowledge and tools. It grounds responses in full-text papers from top-tier computer science conferences, helping researchers conduct literature reviews, brainstorm ideas, design experiments, write academic papers, and evaluate research. It also provides research best practices and traceable citations while avoiding noise from the open web.

An open-source platform for AI conversations, models, and tools LibreChat is an open-source AI platform that brings conversations with multiple AI models together in one customizable interface. It supports models from providers including Anthropic, AWS, OpenAI, and Azure, alongside tools for agents, code execution, web search, and integrations.